Relational Over-Regularization: Graph-Based AI-Generated Text Detection via Sentence Transition Deviation

• URL: http://arxiv.org/abs/2608.26694v1
• Date: Thu, 27 Aug 2026 06:51:40 GMT
• Title: Relational Over-Regularization: Graph-Based AI-Generated Text Detection via Sentence Transition Deviation
• Abstract summary: CrossSource Stylometric Fingerprint (CSFG) is a graph-based framework that encodes positional, sequential, semantic and transition deviation signals as learnable GNN edge features.<n>CSFG achieves 97.14% accuracy under binary detection, outperforming the strongest graph-based baseline by 11.14 pp.
• Score: 4.4331439696271415
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Detecting AI-generated text (AIGT) remains challenging because existing approaches rely on token-level statistical signals or independent stylometric features, causing them to overfit to specific generators and fail under distribution shift. We identify a structural signal at the sentence-pair level: LLMs produce inter-sentence transition variance that deviates from human writing through inflated variance driven by recurring similarity bursts at paragraph boundaries and templated transitions. We formalize this as Relational Over-Regularization (ROR) and validate it across four benchmarks (p < 0.001). The central contribution is this relational problem formulation, not a novel GNN architecture; CSFG is one concrete instantiation for operationalizing ROR. To exploit this signal, we propose the Cross-Source Stylometric Fingerprint Graph (CSFG), a graph-based framework that encodes positional, sequential, semantic, and transition deviation signals as learnable GNN edge features. The per-edge signed deviation δ_ij operationalizes ROR without hand-crafted thresholds and acts as a false-positive calibrator. CSFG achieves 97.14% accuracy under binary detection, outperforming the strongest graph-based baseline by 11.14 pp, with a false-positive rate of 1.57% and robust generalization to unseen LLMs in the inflated-variance regime; detection degrades for generators whose transition variance falls at or below the human baseline.

Related papers

• LoRC: Detecting AI-Generated Images via Low-Rank Collapse in Semantic Residuals [50.157719466558696]
  We show that modern generators exhibit low-rank collapse in the semantic-residual subspace while preserving the dominant semantic direction.<n>We propose textbfLoRC, a framework that decouples semantic dominance to capture the collapsed residual geometry.<n>Our method improves accuracy by an average of 7.0% across multiple benchmarks and achieves 97.0% accuracy on 39 unseen generators.
  arXiv  Detail & Related papers  (2026-08-21T08:58:47Z)
• Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics [49.443264461057645]
  Diffusion and continuous flow-based language models have emerged as the leading non-autoregressive alternatives to language modeling.<n>Progress in both paradigms is overwhelmingly tracked by generative perplexity (gen-PPL): the per-token negative log-likelihood of samples under a frozen autoregressive (AR) scorer.<n>We argue that this metric is unsound. By construction, gen-PPL measures only predictability under the scoring AR, not grammaticality or semantic coherence.
  arXiv  Detail & Related papers  (2026-06-07T02:35:56Z)
• When Attribution Patching Lies: Diagnosis and a Second-Order Correction [9.338965648455238]
  We show that the dominant error stems from the non-linearities in the downstream network rather than local curvature at the patched component.<n>This insight yields three practical tools: (i) a reliability score to detect untrustworthy estimates, (ii) error bounds quantifying potential attribution mis-specifications, and (iii) a Hessian-vector-product correction that eliminates the leading-order error with only one additional backward pass.
  arXiv  Detail & Related papers  (2026-06-05T05:20:32Z)
• A Doeblin-Anchored Contrastive Chart for Learning Markov Transition Kernels [1.2691047660244335]
  This paper introduces a statistical-to-dynamical coordinate framework for learning transition kernels from contrastive objectives.<n>We prove that the anchored contrastive risk identifies the anchored transition density and calibrates excess risk to density error.
  arXiv  Detail & Related papers  (2026-06-01T13:26:44Z)
• Rethinking Feature Alignment in Generalist Graph Anomaly Detection: A Relational Fingerprint-based Approach [60.199985286210904]
  Generalist graph anomaly detection (GAD) aims to detect anomalies on unseen graphs without graph-specific retraining.<n>Existing approaches primarily focus on aligning heterogeneous data across domains, which ignores different feature semantics.<n>We propose Fingerprint-based generalist GAD approach (ReFi-GAD)<n>We show that ReFi-GAD significantly outperforms state-of-the-art methods in experiments on 14 datasets.
  arXiv  Detail & Related papers  (2026-05-25T05:12:26Z)
• Sparse-by-Design Cross-Modality Prediction: L0-Gated Representations for Reliable and Efficient Learning [0.0]
  A unified sparsification primitive would make accuracy-efficiency trade-offs comparable across modalities.<n>We propose a modality-agnostic, feature-wise hard-concrete gating framework that enforces L0-style sparsity directly on learned representations.
  arXiv  Detail & Related papers  (2026-03-26T03:33:42Z)
• Generalizing GNNs with Tokenized Mixture of Experts [75.8310720413187]
  We show that improving stability requires reducing reliance on shift-sensitive features, leaving an irreducible worst-case generalization floor.<n>We propose STEM-GNN, a pretrain-then-finetune framework with a mixture-of-experts encoder for diverse computation paths.<n>Across nine node, link, and graph benchmarks, STEM-GNN achieves a stronger three-way balance, improving robustness to degree/homophily shifts and to feature/edge corruptions while remaining competitive on clean graphs.
  arXiv  Detail & Related papers  (2026-02-09T22:48:30Z)
• TASTE: Task-Aware Out-of-Distribution Detection via Stein Operators [2.191505742658975]
  TASTE (Task-Aware STEin operators) is a task-aware framework based on so-called Stein operators.<n>We show that the resulting operator admits a clear geometric interpretation as a projection of distribution shift onto the sensitivity field of the model.
  arXiv  Detail & Related papers  (2026-02-07T17:48:08Z)
• Variational Bayesian Flow Network for Graph Generation [54.94088904387278]
  We propose Variational Bayesian Flow Network (VBFN) for graph generation.<n>VBFN performs variational lifting to a tractable joint Gaussian variational belief family governed by structured precisions.<n>On synthetic and molecular graph datasets, VBFN improves fidelity and diversity, and surpasses baseline methods.
  arXiv  Detail & Related papers  (2026-01-30T03:59:38Z)
• Structural Alignment Improves Graph Test-Time Adaptation [17.564393890432193]
  We introduce Test-Time Structural Alignment (TSA), a novel algorithm for Graph Test-Time Adaptation (GTTA)<n>TSA aligns graph structures during inference without accessing the source data.<n>Experiments on synthetic and real-world datasets demonstrate TSA's consistent outperformance of both non-graph TTA methods and state-of-the-art GTTA baselines.
  arXiv  Detail & Related papers  (2025-02-25T16:26:25Z)
• Sequence Transduction with Graph-based Supervision [96.04967815520193]
  We present a new transducer objective function that generalizes the RNN-T loss to accept a graph representation of the labels. We demonstrate that transducer-based ASR with CTC-like lattice achieves better results compared to standard RNN-T.
  arXiv  Detail & Related papers  (2021-11-01T21:51:42Z)
• Tail-to-Tail Non-Autoregressive Sequence Prediction for Chinese Grammatical Error Correction [49.25830718574892]
  We present a new framework named Tail-to-Tail (textbfTtT) non-autoregressive sequence prediction. Considering that most tokens are correct and can be conveyed directly from source to target, and the error positions can be estimated and corrected. Experimental results on standard datasets, especially on the variable-length datasets, demonstrate the effectiveness of TtT in terms of sentence-level Accuracy, Precision, Recall, and F1-Measure.
  arXiv  Detail & Related papers  (2021-06-03T05:56:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.